Why Model Averaging?

Fletcher, David

doi:10.1007/978-3-662-58541-2_1

Cited by 11 publications

(16 citation statements)

References 243 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To test the strength of this model, we ran model averaging ( Freckleton, 2011 ). Model averaging tests whether the effect of the update bias was contingent on entering a specific set of variables in the model ( Fletcher, 2018 ). This approach involves running every single combination of models given the independent variables.…”

Section: Methodsmentioning

confidence: 99%

Belief updating in bipolar disorder predicts time of recurrence

Ossola

Garrett

Sharot

et al. 2020

eLife

View full text Add to dashboard Cite

Bipolar disorder is a chronic relapsing condition in which mood episodes are interspersed with periods of wellbeing (euthymia). Shorter periods of euthymia are associated with poorer functioning, so it is crucial to identify predictors of relapse to facilitate treatment. Here, we test the hypothesis that specific valence-dependent learning patterns emerge prior to the clinical manifestation of a relapse, predicting its timing. The ability to update beliefs in response to positive and negative information was quantified in bipolar patients during euthymia, who were then monitored for 5 years. We found that reduced tendency to update beliefs in response to positive relative to negative information predicted earlier relapse. Less updating in response to positive information may generate pessimistic beliefs, which in turn can lead to more severe prodromal symptoms (e.g. sleep disturbance, irritability etc.). The results suggest that measuring valence-dependent belief updating could facilitate risk prediction in bipolar disorder.

show abstract

Section: Methodsmentioning

confidence: 99%

Belief updating in bipolar disorder predicts time of recurrence

Ossola

Garrett

Sharot

et al. 2020

eLife

View full text Add to dashboard Cite

show abstract

“…A decision on whether to model-average based on AIC or BIC is well-debated in the literature. Fletcher (2019) suggests that AIC weights should be better than BIC weights, as model averaging is about estimation and prediction and this is the goal of AIC. In contrast, BIC is focused on identifying the true model.…”

Section: Discussionmentioning

confidence: 99%

“…For a fuller discussion of this, see Yang (2005). Some alternative criteria for model-averaging have been reviewed in Dormann et al (2018) and a systematic review of the state of the art is given in Chapter 3 of Fletcher (2019).…”

Section: Discussionmentioning

confidence: 99%

Multiple System Estimation of Victims of Human Trafficking: Model Assessment and Selection

Cruyff

Overstall

Papathomas

et al. 2020

Crime & Delinquency

View full text Add to dashboard Cite

Recently, multiple systems estimation (MSE) has been applied to estimate the number of victims of human trafficking in different countries. The estimation procedure consists of a log-linear analysis of a contingency table of population registers and covariates. As the number of potential models increases exponentially with the number of registers and covariates, it is practically impossible to fit and compare all models. Therefore, the model search needs to be restricted to a small subset of all potential models. This paper addresses principles and criteria for model assessment and selection for MSE of human trafficking with special attention to sparsity which is typical to human trafficking data. The concepts are illustrated on data from Slovakia and Romania.

show abstract

“…One way to avoid overfitting is to employ model averaging, or ensemble, approaches [84]. By balancing the bias versus variance trade-off, ensemble approaches have been shown to improve prediction accuracy in many fields not just for empirical [83], but also for mechanistic models (for example, [85,86]).…”

Section: Overfittingmentioning

confidence: 99%

Virtual Populations for Quantitative Systems Pharmacology Models

Cheng¹,

Straube²,

Alnaif³

et al. 2021

Preprint

View full text Add to dashboard Cite

Quantitative systems pharmacology (QSP) places an emphasis on dynamic systems modeling, incorporating considerations from systems biology modeling and pharmacodynamics. The goal of QSP is often to quantitatively predict the effects of clinical therapeutics, their combinations, and their doses on clinical biomarkers and endpoints. In order to achieve this goal, strategies for incorporating clinical data into model calibration are critical. Virtual population (VPop) approaches facilitate model calibration while faced with challenges encountered in QSP model application, including modeling a breadth of clinical therapies, biomarkers, endpoints, utilizing data of varying structure and source, capturing observed clinical variability, and simulating with models that may require more substantial computational time and resources than often found in pharmacometrics applications. VPops are frequently developed in a process that may involve parameterization of isolated pathway models, integration into a larger QSP model, incorporation of clinical data, calibration, and quantitative validation that the model with the accompanying, calibrated VPop is suitable to address the intended question or help with the intended decision. Here, we introduce previous strategies for developing VPops in the context of a variety of therapeutic and safety areas: metabolic disorders, drug-induced liver injury, auto-immune diseases, and cancer. We introduce methodological considerations, prior work for sensitivity analysis and VPop algorithm design, and potential areas for future advancement. Finally, we give a more detailed application example of a VPop calibration algorithm that illustrates recent progress and many of the methodological considerations. In conclusion, although methodologies have varied, VPop strategies have been successfully applied to give valid clinical insights and predictions with the assistance of carefully defined and designed calibration and validation strategies. While a uniform VPop approach for all potential QSP applications may be challenging given the heterogeneity in use considerations, we anticipate continued innovation will help to drive VPop application for more challenging cases of greater scale while developing new rigorous methodologies and metrics.

show abstract

Why Model Averaging?

Cited by 11 publications

References 243 publications

Belief updating in bipolar disorder predicts time of recurrence

Belief updating in bipolar disorder predicts time of recurrence

Multiple System Estimation of Victims of Human Trafficking: Model Assessment and Selection

Virtual Populations for Quantitative Systems Pharmacology Models

Contact Info

Product

Resources

About